Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16072
    Prev
    Next
    INDEX
    Explanations

    words related to code or syntax

    oai_token-act-pair · gpt-3.5-turbo

    emphasized or highlighted phrases that start with the character "Ļ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     litter
    -0.69
     vulner
    -0.66
     Alban
    -0.63
    ©¶æ
    -0.62
     Negro
    -0.62
     paran
    -0.60
     township
    -0.59
     negro
    -0.59
     accomp
    -0.58
     Chattanooga
    -0.58
    POSITIVE LOGITS
    ï¸ı
    1.02
    sure
    0.93
    ship
    0.92
    ski
    0.90
    tre
    0.90
    except
    0.86
    Pg
    0.86
    mand
    0.86
    hood
    0.85
    worthiness
    0.85
    Activations Density 0.360%

    No Known Activations